INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

references to political or legal actions and their implications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

omorph

-0.72

 prototyp

-0.64

 ideally

-0.58

 nonex

-0.57

 dynamically

-0.54

inite

-0.54

 fram

-0.54

 transl

-0.54

ãģį

-0.53

 dupl

-0.53

POSITIVE LOGITS

 Belfast

1.20

 REUTERS

0.92

↵

0.87

AFP

0.87

 criticised

0.87

↵↵

0.82

 Copyright

0.80

 Â©

0.80

 apologised

0.80

Activations Density 0.770%

locations or places

references to political or legal actions and their implications

No Comments

No Known Activations